Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 15132
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to motions and judgments in court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.66
    بوابة
    -0.65
    kmäler
    -0.65
    Попис
    -0.64
     Мексичка
    -0.63
    SizeF
    -0.63
     ControllerBase
    -0.62
     BoxFit
    -0.61
    GIVEREF
    -0.61
    ValueGeneration
    -0.61
    POSITIVE LOGITS
     requests
    0.64
     request
    0.64
    requests
    0.60
    request
    0.59
    Requests
    0.52
     Antrag
    0.51
    vraag
    0.50
     proposal
    0.50
    AndroidJUnit
    0.49
    Request
    0.48
    Activations Density 0.773%

    No Known Activations